llmrun
GoogleGemma 3

Gemma 3 4B Pt — Hardware Requirements & GPU Compatibility

Vision

Gemma 3 4B PT represents Google's pretrained checkpoint at the lower end of the Gemma 3 family, containing roughly 4.3 billion parameters when vision components are included. This model employs a vision-language architecture capable of handling both text and images. The "PT" suffix indicates its status as a base model: it lacks instruction tuning and cannot reliably follow chat prompts, making it suitable for fine-tuning, research, or experimentation instead of direct use as an assistant. Given its size, the quantized version runs on nearly any recent GPU or even a CPU, though the instruction-tuned release remains the better choice for actual conversation. Similar to the larger Gemma 3 models, it supports a context window of up to 128K tokens. Distribution follows the Gemma Terms of Use, and users must acknowledge this license on Hugging Face to gain access. Released in February 2025, it stands as one of the smaller pretrained options within the Gemma 3 lineup, sitting alongside the 12B and 27B variants.

4.3B params · denseGemma Terms285.4K downloads180 likes1.2K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 32KBest on24 GB Q4_K_M · ~231 tok/s · 32KMacs from8 GB Q4_K_M · ~25 tok/s

Gemma Terms

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Gemma 3 4B Pt

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama
one command · needs Ollama installed
$ollama run hf.co/mradermacher/gemma-3-4b-pt-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 19.0 GB free · 16K context

Download: gemma-3-4b-pt.Q4_K_M.gguf2.49 GBmradermacher

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does Gemma 3 4B Pt Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
2.0 GB6.6 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~326 tok/s
2.1 GB6.7 GB3-bit small — 3-bit small quantizationFits: 32K context · ~317 tok/s
2.3 GB6.9 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~284 tok/s
2.4 GB7 GB4-bit · legacy — 4-bit legacy quantizationFits: 32K context · ~277 tok/s
2.8 GB7.5 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~231 tok/s
3.4 GB8 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~194 tok/s
3.9 GB8.5 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~168 tok/s
4.7 GB9.4 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~139 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

5.0GBat 16K context

Weights
2.2 GB
KV cache
2.5 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 19.0 GB free · ~231 tok/s

≥50 tok/s needs ≥218 GB/s · RTX 5090 ~410, M5 Ultra ~303

Which Hardware Can Run Gemma 3 4B Pt?

Q4_K_M · 2.8 GB

Gemma 3 4B Pt (Q4_K_M) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce GTX 1650 SUPER. 185 devices with unified memory can run Gemma 3 4B Pt, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 5 GB · ~62 tok/s · 32K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 5 GB · ~82 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 5 GB · ~103 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 5 GB · ~231 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 5 GB · ~30 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 5 GB · ~135 tok/s · 32KMacs →

Alternatives to Gemma 3 4B Pt

Gemma 3 family · 20 models →

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Spark X2.6 4BXHToken—4.3 GB~221same size
Granite Vision 4.1 4BIBM—4 GB~228same size
Qwen3 VL 4B InstructAlibaba—4.5 GB~208same size
MiniCPM V 4OpenBMB—3.1 GB~236same size
Phi 3.5 Vision InstructMicrosoft—9.2 GB~183same size
NVIDIA Nemotron 3.5 Bolt E4B 4GBNVIDIA—4.8 GB~248same size
Fine-tunes & variants(1)

Specifications

Publisher
Google
Family
Gemma 3
Parameters
4.3B
Release Date
2025-02-20
License
Gemma Terms

Frequently Asked Questions

How much VRAM does Gemma 3 4B Pt need?

Gemma 3 4B Pt requires 2.8 GB of VRAM at Q4_K_M, or 9.5 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 4.3B × 4.8 bits ÷ 8 = 2.6 GB

KV Cache + Overhead ≈ 0.2 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

VRAM usage by quantization

2.8 GB

Learn more about VRAM estimation →

What's the best quantization for Gemma 3 4B Pt?

For Gemma 3 4B Pt, Q4_K_M (2.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (3.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.3 GB.

VRAM requirement by quantization

IQ2_XXS
1.3 GB
IQ3_XS
1.9 GB
Q4_0
2.4 GB
IQ4_NL
2.7 GB
Q4_K_M ★
2.8 GB
BF16
9.5 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Gemma 3 4B Pt on a Mac?

Yes — Mac Mini M2 (8 GB) and 158 other Macs can run Gemma 3 4B Pt. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.8 GB of usable unified memory (RAM minus macOS overhead).

Can I run Gemma 3 4B Pt locally?

Yes — Gemma 3 4B Pt can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Gemma 3 4B Pt?

At Q4_K_M, Gemma 3 4B Pt can reach ~1690 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~231 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 2.84 × 0.65 = ~1831 tok/s

Estimated speed at Q4_K_M (2.8 GB)

~1831 tok/s
~231 tok/s
~1831 tok/s
~1690 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Gemma 3 4B Pt?

At Q4_K_M, the download is about 2.58 GB. The full-precision BF16 version is 8.60 GB. The smallest option (IQ2_XXS) is 1.18 GB.

Which GPUs can run Gemma 3 4B Pt?

114 consumer GPUs can run Gemma 3 4B Pt at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB, NVIDIA GeForce GTX 1050 Ti. 107 GPUs have plenty of headroom for comfortable inference.

Which devices can run Gemma 3 4B Pt?

185 devices with unified memory can run Gemma 3 4B Pt at Q4_K_M (2.8 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.